{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:35:02Z","timestamp":1745627702334,"version":"3.40.2"},"reference-count":34,"publisher":"Institution of Engineering and Technology (IET)","issue":"11","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["4232026"],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272049","62171042","61871039","62102033","62006020"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2024,9]]},"abstract":"Abstract<\/jats:title>Traffic sign detection is critical for autonomous driving technology. However, accurately detecting traffic signs in complex traffic environments remains challenge despite the widespread use of one\u2010stage detection algorithms known for their real\u2010time processing capabilities. In this paper, the authors propose a traffic sign detection method based on YOLO v8. Specifically, this study introduces the Space\u2010to\u2010Depth (SPD) module to address missed detections caused by multi\u2010scale variations of traffic signs in traffic scenes. The SPD module compresses spatial information into depth channels, expanding the receptive field and enhancing the detection capabilities for objects of varying sizes. Furthermore, to address missed detections caused by complex backgrounds such as trees, this paper employs the Select Kernel attention mechanism. This mechanism enables the model to dynamically adjust its focus and more effectively concentrate on key features. Additionally, considering the uneven distribution of training data, the authors adopted the WIoUv3 loss function, which optimizes loss calculation through a weighted approach, thereby improving the model's detection performance across various sizes and frequencies of instances. The proposed methods were validated on the CCTSDB and TT100K datasets. Experimental results demonstrate that the authors\u2019 method achieves substantial improvements of 3.2% and 5.1% on the mAP50 metric compared to YOLOv8s, while maintaining high detection speed, significantly enhancing the overall performance of the detection system. The code for this paper is located at https:\/\/github.com\/dusongjie\/TSD\u2010YOLO\u2010Small\u2010Traffic\u2010Sign\u2010Detection\u2010Based\u2010on\u2010Improved\u2010YOLO\u2010v8<\/jats:ext-link><\/jats:p>","DOI":"10.1049\/ipr2.13141","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T05:42:19Z","timestamp":1717479739000},"page":"2884-2898","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["TSD\u2010YOLO: Small traffic sign detection based on improved YOLO v8"],"prefix":"10.1049","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4730-4639","authenticated-orcid":false,"given":"Songjie","family":"Du","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2293-1004","authenticated-orcid":false,"given":"Weiguo","family":"Pan","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]},{"given":"Nuoya","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]},{"given":"Songyin","family":"Dai","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3340-4215","authenticated-orcid":false,"given":"Bingxin","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]},{"given":"Hongzhe","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]},{"given":"Cheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]},{"given":"Xuewei","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Information Service Engineering Beijing Union University Beijing China"},{"name":"College of Robotics Beijing Union University Beijing China"}]}],"member":"265","published-online":{"date-parts":[[2024,6,3]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"crossref","unstructured":"Redmon J. Divvala S. Girshick R. et\u00a0al.:You only look once: Unified real\u2010time object detection. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp.779\u2013788(2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_10_3_1","doi-asserted-by":"crossref","unstructured":"Redmon J. Farhadi A.:YOLO9000: Better faster stronger. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp.7263\u20137271(2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_2_10_4_1","unstructured":"Redmon J. Farhadi A.:Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"e_1_2_10_5_1","unstructured":"Bochkovskiy A. Wang C.Y. Liao H.Y.M.:Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"e_1_2_10_6_1","unstructured":"Li C. Li L. Jiang H. et\u00a0al.:YOLOv6: A single\u2010stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"e_1_2_10_7_1","doi-asserted-by":"crossref","unstructured":"Wang C.Y. Bochkovskiy A. Liao H.Y.M.:YOLOv7: Trainable bag\u2010of\u2010freebies sets new state\u2010of\u2010the\u2010art for real\u2010time object detectors. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp.7464\u20137475(2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"Liu W. Anguelov D. Erhan D. et\u00a0al.:SSD: Single shot multibox detector. In:Computer Vision\u2013ECCV 2016: 14th European Conference Amsterdam The Netherlands 11\u201314 October 2016 Proceedings Part I 14.Springer International Publishing pp.21\u201337(2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"Lin T.Y. Goyal P. Girshick R. et\u00a0al.:Focal loss for dense object detection. In:Proceedings of the IEEE International Conference on Computer Vision pp.2980\u20132988(2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3170354"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-022-01252-w"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2022.116783"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22134833"},{"key":"e_1_2_10_14_1","doi-asserted-by":"crossref","unstructured":"Khokhar S. Kedia D. Dahiya P.K.:License plate detection techniques: Conventional methods to deep learning. In:ICT with Intelligent Applications: Proceedings of ICTIS 2022 vol1 pp.729\u2013734.Springer Nature Singapore Singapore(2022)","DOI":"10.1007\/978-981-19-3571-8_66"},{"issue":"6","key":"e_1_2_10_15_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.jksuci.2023.101567","article-title":"DARGS: Image inpainting algorithm via deep attention residuals group and semantics","volume":"35","author":"Chen Y.","year":"2023","journal-title":"J. King Saud Univ."},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-08077-5"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23083871"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111392"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123111"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1504\/IJCVR.2024.10062468"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02813-1"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3349464"},{"key":"e_1_2_10_23_1","first-page":"1","article-title":"Research and implementation of an embedded traffic sign detection model using improved YOLOV5","author":"Hu T.","year":"2024","journal-title":"Int. J. Automot. Technol."},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"Girshick R. Donahue J. Darrell T. et\u00a0al.:Rich feature hierarchies for accurate object detection and semantic segmentation. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition pp.580\u2013587(2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_10_25_1","doi-asserted-by":"crossref","unstructured":"Girshick R.:Fast R\u2010CNN. In:Proceedings of the IEEE International Conference on Computer Vision pp.1440\u20131448(2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/3825532","article-title":"Traffic sign detection via improved sparse R\u2010CNN for autonomous vehicles","volume":"2022","author":"Liang T.","year":"2022","journal-title":"J. Adv. Transp."},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04230-4"},{"key":"e_1_2_10_29_1","first-page":"1","article-title":"Toward effective traffic sign detection via two\u2010stage fusion neural networks","author":"Li Z.","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"Li X. Wang W. Hu X. et\u00a0al.:Selective kernel networks. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition pp.510\u2013519(2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"Sunkara R. Luo T.:No more strided convolutions or pooling: A new CNN building block for low\u2010resolution images and small objects. In:Joint European Conference on Machine Learning and Knowledge Discovery in Databases pp.443\u2013445.Springer Nature Switzerland Cham(2022)","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"e_1_2_10_32_1","unstructured":"Tong Z. Chen Y. Xu Z. et\u00a0al.:Wise\u2010IoU: Bounding box regression loss with dynamic focusing mechanism. arXiv preprint arXiv:2301.10051 (2023)"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24030989"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3241234"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.3233\/AIS-220038"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.13141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T13:02:44Z","timestamp":1742648564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.13141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":34,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["10.1049\/ipr2.13141"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.13141","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"type":"print","value":"1751-9659"},{"type":"electronic","value":"1751-9667"}],"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-02-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}